{"id":"W4390604119","doi":"10.1109/tpami.2024.3350450","title":"Regularized Loss With Hyperparameter Estimation for Weakly Supervised Single Class Segmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Hyperparameter; Segmentation; Computer science; Pattern recognition (psychology); Image segmentation; Conditional random field; Ground truth; Pixel; Machine learning; Scale-space segmentation","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003901084,0.001811101,0.002190036,0.001454725,0.0007500101,0.002003998,0.003146772,0.003131497,0.002433683],"category_scores_gemma":[0.009646326,0.0008144621,0.001579054,0.001291116,0.001844628,0.003741624,0.002619944,0.003208922,0.00159474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002238277,"about_ca_system_score_gemma":0.001721709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003650008,"about_ca_topic_score_gemma":0.004592679,"domain_scores_codex":[0.9976399,0.0007492119,0.000123197,0.0007486131,0.0005181596,0.0002209701],"domain_scores_gemma":[0.9960665,0.001596199,0.0004238974,0.001177848,0.0005579076,0.0001776607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005447186,0.0002452433,0.003420187,0.0002428583,0.0002018404,0.000205239,0.0002632482,0.7111362,0.01527683,0.0193835,0.009920328,0.2391598],"study_design_scores_gemma":[0.00001076594,0.0000407835,0.0003398743,0.00001340974,0.00001048662,0.00005824248,0.00001294654,0.9829007,0.002485188,0.01316733,0.0009474035,0.00001295368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0158215,0.00025787,0.9801084,0.0002415472,0.00003114811,0.00007519718,0.0002353401,0.002115457,0.001113464],"genre_scores_gemma":[0.45169,0.0003945979,0.5333223,0.001017027,0.0002367727,0.0006143493,0.00336553,0.002026351,0.007333198],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003901084,"threshold_uncertainty_score":0.02063113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02345517721428979,"score_gpt":0.2795068314920156,"score_spread":0.2560516542777257,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}